© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39799
    Prev
    Next
    INDEX
    Explanations

    medical school, internship, and residency"- "pharmacokinetics and safety differences... in patients"- "Nosocomial bacterial and fungal meningitis in children"- "implements org.hibernate."- "Swift 3"- "Business & IT Drivers"

    np_acts-logits-general · gemini-2.5-flash-lite

    technical or professional content in documents, particularly related to programming, medical, or business fields.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     my
    -1.15
     develop
    -1.12
    lında
    -1.06
     you
    -1.05
    Since
    -1.01
     Since
    -1.00
     predominant
    -1.00
    ɴ
    -0.99
    Ꭺ
    -0.96
     vy
    -0.96
    POSITIVE LOGITS
     ail
    1.27
     envíos
    1.26
     zelve
    1.23
     réunis
    1.20
     jį
    1.20
     chargés
    1.16
    こい
    1.16
    områ
    1.15
     nė
    1.13
     compét
    1.13
    Activations Density 0.173%

    No Known Activations